fix: 改进正文提取，支持政采云 SPA API 和大化县政府网 div.article-con

- 新增 _extract_zcy_content(): 通过政采云隐藏 API 获取公告正文
- 新增 _extract_dahuagov_content(): 大化县专用提取，支持 div.article-con
- 通用提取器新增更多选择器

app/crawler/parsers.py

@@ -151,8 +151,21 @@ def parse_dahuagov_detail_pubdate(html: str) -> datetime | None:
 
 async def extract_page_content(url: str, timeout: int = 30) -> str | None:
     """抓取详情页并用 BeautifulSoup 提取正文纯文本"""
+    import urllib.parse
+
     import httpx
 
+    # ---- 站点专用处理 ----
+
+    # ① 政采云 SPA (HTTP API, 无需渲染)
+    if "zfcg.gxzf.gov.cn" in url and "articleId=" in url:
+        return await _extract_zcy_content(url, timeout)
+
+    # ② 大化县政府网 (静态HTML)
+    if "www.gxdh.gov.cn" in url or "gxdh.gov.cn" in url:
+        return await _extract_dahuagov_content(url, timeout)
+
+    # ---- 通用 HTML 提取 ----
     try:
         headers = {
             "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36",
@@ -172,15 +185,16 @@ async def extract_page_content(url: str, timeout: int = 30) -> str | None:
                 "div.Custom_UnionStyle", "div.pages_content", "div#content",
                 "div.main-content", "article", ".article", ".detail-content",
                 ".text-content", ".news-content", ".detail-article",
+                "div.article-con", ".trs_editor_view", ".TRS_UEDITOR",
+                ".trs_paper_default", ".article-content",
             ]
             for selector in selectors:
                 container = soup.select_one(selector)
                 if container:
-                    # 移除脚本和样式
                     for tag in container.find_all(["script", "style"]):
                         tag.decompose()
                     text = container.get_text(separator="\n", strip=True)
-                    if len(text) > 50:  # 至少50字才算有效正文
+                    if len(text) > 50:
                         return text
 
             # 兜底：取 body 内所有文本
@@ -189,9 +203,8 @@ async def extract_page_content(url: str, timeout: int = 30) -> str | None:
                 for tag in body.find_all(["script", "style", "nav", "footer", "header"]):
                     tag.decompose()
                 text = body.get_text(separator="\n", strip=True)
-                # 移除过长的空白行
                 lines = [l.strip() for l in text.split("\n") if l.strip()]
-                text = "\n".join(lines[:200])  # 最多取前200行
+                text = "\n".join(lines[:200])
                 if len(text) > 50:
                     return text
 
@@ -200,6 +213,109 @@ async def extract_page_content(url: str, timeout: int = 30) -> str | None:
         return None
 
 
+async def _extract_zcy_content(url: str, timeout: int = 30) -> str | None:
+    """从政采云 SPA 隐藏 API 提取公告正文"""
+    import urllib.parse
+
+    import httpx
+    from bs4 import BeautifulSoup
+
+    params = urllib.parse.parse_qs(urllib.parse.urlparse(url).query)
+    article_id = params.get("articleId", [None])[0]
+    parent_id = params.get("parentId", [None])[0]
+    if not article_id:
+        return None
+
+    api_url = "https://zfcg.gxzf.gov.cn/portal/detail"
+    if parent_id:
+        api_url += f"?articleId={article_id}&parentId={parent_id}"
+    else:
+        api_url += f"?articleId={article_id}"
+
+    headers = {
+        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36",
+        "Accept": "application/json, text/plain, */*",
+        "Referer": url,
+    }
+
+    try:
+        async with httpx.AsyncClient(timeout=timeout) as client:
+            resp = await client.get(api_url, headers=headers)
+            if resp.status_code != 200:
+                return None
+
+            data = resp.json()
+            if not data.get("success"):
+                return None
+
+            content_html = data.get("result", {}).get("data", {}).get("content", "")
+            if not content_html:
+                return None
+
+            soup = BeautifulSoup(content_html, "html.parser")
+            for tag in soup.find_all(["script", "style"]):
+                tag.decompose()
+            text = soup.get_text(separator="\n", strip=True)
+
+            # 清理过短行和多余空白
+            lines = [l.strip() for l in text.split("\n") if len(l.strip()) > 5]
+            text = "\n".join(lines[:300])
+            return text if len(text) > 50 else None
+    except Exception:
+        return None
+
+
+async def _extract_dahuagov_content(url: str, timeout: int = 30) -> str | None:
+    """从大化县政府网详情页提取正文"""
+    import httpx
+    from bs4 import BeautifulSoup
+
+    headers = {
+        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36",
+        "Accept": "text/html,application/xhtml+xml",
+        "Accept-Language": "zh-CN,zh;q=0.9",
+    }
+
+    try:
+        async with httpx.AsyncClient(timeout=timeout, follow_redirects=True) as client:
+            resp = await client.get(url, headers=headers)
+            if resp.status_code != 200:
+                return None
+
+            soup = BeautifulSoup(resp.text, "html.parser")
+
+            # 大化县政府网正文容器
+            selectors = [
+                "div.article-con", ".trs_editor_view", ".TRS_UEDITOR",
+                ".trs_paper_default", "div.content", "div.TRS_Editor",
+                "div.article-content", "div.Custom_UnionStyle",
+                "div#content", "div.main-content", "article", ".detail-content",
+            ]
+            for selector in selectors:
+                container = soup.select_one(selector)
+                if container:
+                    for tag in container.find_all(["script", "style"]):
+                        tag.decompose()
+                    text = container.get_text(separator="\n", strip=True)
+                    if len(text) > 50:
+                        lines = [l.strip() for l in text.split("\n") if l.strip()]
+                        return "\n".join(lines[:300])
+
+            # 兜底
+            body = soup.find("body")
+            if body:
+                for tag in body.find_all(["script", "style", "nav", "footer", "header"]):
+                    tag.decompose()
+                text = body.get_text(separator="\n", strip=True)
+                lines = [l.strip() for l in text.split("\n") if l.strip()]
+                text = "\n".join(lines[:200])
+                if len(text) > 50:
+                    return text
+            return None
+    except Exception:
+        return None
+
+
 def _generate_hash(ann: dict[str, Any]) -> str:
     content = (
         f"{ann['title']}|{ann['publish_date'].strftime('%Y-%m-%d')}"